Intelligent operation management and control method and system based on Internet of Things

Abstract

The invention relates to an intelligent operation management and control method and system based on the Internet of Things, and the method comprises the steps: carrying out the positioning of a current worker based on the wireless technology of the Internet of Things, and starting a safety management and control program when the current worker is in place in a corresponding region. In the safety management and control process, the current worker is subjected to video shooting, the action characteristics of the worker are extracted, and safety monitoring is carried out on the worker in real time. If the security risk exists, the alarm information is directly sent to the Internet of Things terminal on the worker, and the behavior of the worker is corrected. The method is suitable for being used in related scenes of operating dangerous equipment, the action compliance of workers can be further guaranteed, and potential safety hazards caused by some non-compliance actions are avoided.

Description

Technical Field

[0001] The present invention relates to the field of business management and control, and in particular to an intelligent business management and control method and system based on the Internet of Things. Background Art

[0002] The characteristics of the power industry determine that its working environment has high risks, including high voltage electricity, high-altitude operations, etc. Once an accident occurs, it may not only cause casualties to workers, but also affect the lives of surrounding residents. Therefore, protecting the personal safety of employees and the public is the primary responsibility of power companies.

[0003] There are a lot of dangerous places in the business premises of the power industry (such as substations). In order to ensure the safety of employees, a lot of safety training is required before they take up their posts. However, even so, relying entirely on the self-consciousness of employees will still pose safety risks. Summary of the invention

[0004] In view of this, an object of the present invention is to provide an intelligent business management and control method and system based on the Internet of Things to solve the potential safety hazards in the prior art.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] The present invention provides an intelligent operation and control method based on the Internet of Things, comprising the steps of:

[0007] Obtaining the task content and indoor location of the current employee, wherein the indoor location is determined based on the distance measurement of multiple IoT base stations and the IoT terminal on the employee;

[0008] Determining the scope of work activities of the current employee based on the task content of the current employee and a pre-built reference database;

[0009] When the indoor location of the current employee falls within the work activity range, collecting a regional video of the work activity range based on a preset camera;

[0010] Extracting a regional image from the regional video, extracting a person image from the regional image, and extracting key points of a human body from the person image, extracting frames from the regional video based on motion features of the key points of the human body to obtain multiple frames of person images, and determining motion features of the current employee based on the key points of the human body in the multiple frames of person images;

[0011] It is determined whether the current employee is at risk based on the action characteristics of the current employee, and when there is a risk, an alarm message is sent to the Internet of Things terminal of the current employee.

[0012] In an embodiment of the present application, obtaining the indoor location of the current employee includes:

[0013] Regularly obtain the distance value S between multiple IoT base stations and the IoT terminal of the current employee i ;

[0014] Based on the coordinates of multiple IoT base stations (x i ,y i ,z i ) and the IoT terminal of the current employee (x 0 ,y 0 ,z 0 ) coordinates to construct multiple distance coordinate formulas, wherein the multiple distance coordinate formulas are:

[0015]

[0016] Based on the least squares method, multiple distance coordinate formulas are fitted to obtain the current employee’s indoor positioning (x 0 ,y 0 ,z 0 ).

[0017] In one embodiment of the present application, the method for constructing the reference database includes:

[0018] S1, obtain historical positioning records corresponding to various tasks;

[0019] S2, merge the positioning points in the historical positioning records of each job into the same coordinate system;

[0020] S3, calculating the average value of all the positioning points in the coordinate system to obtain a reference positioning point; and using the reference positioning point as the current positioning point;

[0021] S4, calculating the distances between all adjacent positioning points of the current positioning point and the current positioning point, and retaining target positioning points whose distances are less than a preset distance threshold;

[0022] S5, taking the retained target positioning point as the current positioning point, and returning to step S4 until all target positioning points are obtained;

[0023] S6, curve fitting is performed on the outermost target positioning points to obtain the work activity range of each job, and a reference database is constructed based on multiple jobs and the work activity ranges of multiple jobs.

[0024] In one embodiment of the present application, extracting a person image from the region image, and extracting key points of a human body from the person image, include:

[0025] A person image in the area image is extracted based on a pre-constructed human recognition model, and human key points in the person image are extracted based on a pre-constructed human feature point recognition model, wherein the human key points include a plurality of human bone joints.

[0026] In one embodiment of the present application, the frame extraction of the regional video based on the motion characteristics of the human body key points includes:

[0027] Get the current time extraction interval T 0 , and extract the interval T based on the current time 0 Extract two image frames and calculate the distance S between the same human key points in the two image frames j , where j is the serial number of the key point of the human body;

[0028] Calculate all distances S j The average And based on the average value S j Calculate the time interval T for the next image extraction 0 ', where the time interval for the next image extraction is T 0 The mathematical expression of ′ is:

[0029]

[0030] Where S is the reference value of the moving distance;

[0031] Based on the time interval T for the next image extraction 0 'Proceed to next frame extraction.

[0032] In one embodiment of the present application, the action features of the current employee based on the key points of the human body of the multiple frames of personnel images include:

[0033] Construct motion vectors based on the same human key points of any two adjacent images of people, and construct motion features based on all motion vectors; and connect the human key points of each frame of the image of the person to obtain posture features;

[0034] An action feature is constructed based on the motion feature and the posture feature.

[0035] In an embodiment of the present application, judging whether the current employee is at risk based on the action characteristics of the current employee includes:

[0036] When there is a dangerous area in the work activity range, determine whether there is a target motion vector located in the dangerous area and whose modulus is greater than a preset length threshold, and match the posture feature with a pre-constructed dangerous posture feature template; when there is a target motion vector, or there is a posture feature that matches the dangerous posture feature template, determine whether the current employee is at risk;

[0037] When there is no dangerous area in the working activity range, the posture feature is matched with a pre-constructed dangerous posture feature template; and when there is a posture feature matching the dangerous posture feature template, it is determined that the current employee is at risk.

[0038] The present application also provides an intelligent business management and control system based on the Internet of Things, including:

[0039] An acquisition module, used to acquire the task content and indoor location of the current employee, wherein the indoor location is determined based on the distance measurement of multiple IoT base stations and the IoT terminal on the employee;

[0040] A scoping module for determining the scope of work activities of a current employee based on the task content of the current employee and a pre-built reference database;

[0041] A video acquisition module, configured to acquire regional video of the work activity range based on a preset camera when the indoor location of the current employee falls within the work activity range;

[0042] A feature extraction module, used to extract a regional image from the regional video, extract a person image from the regional image, and extract key points of a human body from the person image, extract frames of the regional video based on motion features of the key points of the human body to obtain multiple frames of person images, and determine the motion features of the current employee based on the key points of the human body in the multiple frames of person images;

[0043] The security management and control module is used to determine whether the current employee is at risk based on the action characteristics of the current employee, and send an alarm message to the Internet of Things terminal of the current employee when there is a risk.

[0044] The present application also provides an electronic device, the electronic device comprising:

[0045] one or more processors;

[0046] A storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the electronic device implements the intelligent business management and control method based on the Internet of Things as described above.

[0047] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor of a computer, the computer executes the intelligent business management and control method based on the Internet of Things as described above.

[0048] The beneficial effects of the present invention are as follows: an intelligent business management and control method and system based on the Internet of Things of the present invention locates the current staff based on the wireless technology of the Internet of Things, and starts the safety management and control program when the current staff is in place in the corresponding area. During the safety management and control process, the current staff is filmed and the motion characteristics of the staff are extracted to monitor the safety of the staff in real time. If there is a safety risk, the alarm information is directly sent to the Internet of Things terminal on the staff to correct their behavior. The present application is suitable for use in scenarios related to the operation of dangerous equipment, and can further ensure that the staff's actions are in compliance and avoid safety hazards caused by some non-compliant actions. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The present invention will be further described below in conjunction with the accompanying drawings and embodiments:

[0050] Figure 1 This is an application scenario diagram of an intelligent business management and control method based on the Internet of Things shown in an embodiment of the present application;

[0051] Figure 2 It is a flow chart of an intelligent business management and control method based on the Internet of Things shown in an embodiment of the present application;

[0052] Figure 3 It is a structural diagram of an intelligent business management and control system based on the Internet of Things shown in one embodiment of the present application. DETAILED DESCRIPTION

[0053] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0054] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show the layers related to the present invention rather than being drawn according to the number, shape and size of the layers in actual implementation. In actual implementation, the type, quantity and proportion of each layer may be changed arbitrarily, and the layer layout may also be more complicated.

[0055] In the following description, numerous details are discussed to provide a more thorough explanation of embodiments of the present invention; however, it is apparent to one skilled in the art that embodiments of the present invention may be practiced without these specific details.

[0056] Figure 1 This is an application scenario diagram of an intelligent business management and control method based on the Internet of Things shown in an embodiment of the present application, such as Figure 1 As shown, in this application, the daily work of the staff is to operate and control the relevant equipment 110, so their working range is defined as the operating range of the relevant equipment 110. At the same time, based on multiple UWB base stations 120 and the UWB terminal 130 carried by the staff, the staff is positioned in real time. If the staff arrives in the operating range, the subsequent safety control procedures are executed. If the staff is not in the operating range, the UWB terminal 130 can also be used to communicate with the staff about the relevant situation and detect abnormalities in time.

[0057] Figure 2 is a flow chart of an intelligent business management and control method based on the Internet of Things shown in an embodiment of the present application, such as Figure 2 As shown: An intelligent business management and control method based on the Internet of Things in this embodiment may include steps S210 to S250:

[0058] S210, obtaining the task content and indoor positioning of the current employee, wherein the indoor positioning is determined based on the distance measurement of multiple IoT base stations and the IoT terminal on the employee;

[0059] This application is used in power operation and maintenance scenarios, such as substations, distribution stations, etc. Because there is electromagnetic interference in the workplace, the UWB Internet of Things with strong anti-interference ability is selected to achieve remote communication and positioning.

[0060] In this application, the method of performing positioning using UWB Internet of Things includes:

[0061] S211, regularly obtaining the distance value S between multiple IoT base stations and the IoT terminal of the current employee i ;

[0062] UWB ranging is mainly based on the principle of time of flight (ToF), that is, the distance is calculated by measuring the propagation time of the signal from the transmitter to the receiver. Specifically, it includes:

[0063] (1) Ensure that the UWB base station and UWB terminal are correctly configured, including clock synchronization, communication protocol, etc.

[0064] (2) The UWB terminal sends a UWB pulse signal according to a predetermined protocol.

[0065] (3) The UWB base station receives the signal and records the timestamp.

[0066] (4) The UWB base station transmits the received timestamp data to the central processing unit or positioning engine.

[0067] (5) The central processing unit or positioning engine calculates the flight time of the signal based on the timestamp data and then calculates the distance.

[0068] S212, based on the coordinates of multiple IoT base stations (x i ,y i ,z i ) and the IoT terminal of the current employee (x 0 ,y 0 ,z 0 ) coordinates to construct multiple distance coordinate formulas, wherein the multiple distance coordinate formulas are:

[0069]

[0070] S213, fitting multiple distance coordinate formulas based on the least squares method to obtain the indoor location of the current employee (x 0 ,y 0 ,z 0 ).

[0071] The least squares method is a commonly used mathematical optimization technique, which is mainly used to fit data points so that the sum of square errors between the data points and the fitting curve is minimized. Using the least squares method to fit a polynomial is an existing technology and will not be described in detail here.

[0072] S220, determining the work activity scope of the current employee based on the task content of the current employee and a pre-built reference database;

[0073] Since this application is widely used in the control scenarios of power equipment operators, an employee's work activity range is defined around the target power equipment. Within this range, the subsequent control procedures are triggered to avoid wasting resources by long-term operation of cameras and computing equipment. It can also promptly detect abnormal employee leave. The UWB terminal carried by employees is also an information transmission device for subsequent security control.

[0074] In this application, the method for constructing the reference database includes:

[0075] S1, obtain historical positioning records corresponding to various tasks; these records consist of reference positioning of different staff members in their daily work.

[0076] S2, merge the positioning points in the historical positioning records of each job into the same coordinate system;

[0077] S3, calculating the average value of all the positioning points in the coordinate system to obtain a reference positioning point; and using the reference positioning point as the current positioning point; the average value is the centroid of all the positioning points, and density-based clustering is performed on all the positioning points starting from the centroid to obtain a core cluster.

[0078] S4, calculate the distances between all adjacent positioning points of the current positioning point and the current positioning point, and retain the target positioning points whose distances are less than a preset distance threshold; if the distance between the adjacent positioning point and the current positioning point is small, it is determined that there is a clustering feature between the adjacent positioning point and the current positioning point, otherwise it is determined to be a scattered point. The points showing the clustering feature are retained, and the scattered points are eliminated.

[0079] S5, taking the retained target positioning point as the current positioning point and returning to step S4 until all the target positioning points are obtained; after obtaining the clustering points, continue to delineate the clustering points based on the clustering points, and perform clustering layer by layer.

[0080] S6, curve fitting is performed on the outermost target positioning points to obtain the work activity range of each job, and a reference database is constructed based on multiple jobs and the work activity ranges of multiple jobs.

[0081] Finally, after all the clustering points are obtained, the outermost positioning points are used as contour points for fitting to obtain the working activity range of each job and finally construct a reference database.

[0082] S230, when the indoor location of the current employee falls within the work activity range, collecting a regional video of the work activity range based on a preset camera;

[0083] The work activity range of the current employee when performing the current work is determined from the reference database. If the current employee enters the work activity range, the pre-set camera is used to collect the video images. The video images collected by the camera are directly sent to the back-end computing device, or uploaded to the computing device in the cloud to execute subsequent monitoring methods.

[0084] S240, extracting a regional image from the regional video, extracting a person image from the regional image, and extracting key points of a human body from the person image, extracting frames of the regional video based on motion features of the key points of the human body to obtain multiple frames of person images, and determining motion features of the current employee based on the key points of the human body in the multiple frames of the person images;

[0085] The monitoring method flow includes:

[0086] (1) Image extraction

[0087] First, extract the regional image of each frame in the regional video, and the extraction method can be cropping, so that only the image with people is retained.

[0088] (2) Extraction of human contours and key points

[0089] In the present application, deep learning technology is used to extract the person image in the area image based on a pre-built human recognition model, and the human key points in the person image are extracted based on a pre-built human feature point recognition model, wherein the human key points include multiple human bone joints.

[0090] The model construction methods include:

[0091] Data preparation requires a large amount of image data, especially images containing human bodies. These images can be obtained from public datasets such as COCO (Common Objects in Context), MPII Human Pose, Human3.6M, etc. Then the images are annotated to mark the human body contours and feature points (such as joint positions). You can use annotation tools such as LabelMe, LabelBox, etc. for manual annotation, or you can use semi-automatic annotation tools.

[0092] Data preprocessing: scaling images to a uniform size, such as 256x256 or 368x368 pixels. Increase data diversity and improve the generalization of the model through operations such as rotation, scaling, cropping, and flipping. Normalize images, such as normalizing pixel values ​​to between 0 and 1.

[0093] Select the model architecture. Human contour detection can use semantic segmentation models, such as U-Net, DeepLab, etc. Human feature point detection can use key point detection models, such as OpenPose, HRNet (High-Resolution Network), Hourglass, etc.

[0094] Model training, choose the appropriate loss function, such as cross entropy loss (for semantic segmentation) and mean square error loss (for key point detection). During training, use GPU to accelerate the training process, set the appropriate batch size, learning rate, and number of training rounds (epochs).

[0095] Verification and adjustment, finally, the model performance is evaluated on the validation set, and the model parameters and hyperparameters are adjusted according to the verification results.

[0096] (3) Dynamic frame extraction

[0097] In order to reduce the computing load, this application uses a dynamic frame extraction method to extract personnel images, specifically including:

[0098] Get the current time extraction interval T 0 , and extract the interval T based on the current time 0 Extract two image frames and calculate the distance S between the same human key points in the two image frames j , where j is the serial number of the key point of the human body;

[0099] Calculate all distances S j The average And based on the average value S j Calculate the time interval T for the next image extraction 0 ', where the time interval for the next image extraction is T 0 The mathematical expression of ′ is:

[0100]

[0101] Where S is the reference value of the moving distance;

[0102] Based on the time interval T for the next image extraction 0 'Proceed to next frame extraction.

[0103] In this application, the previous time interval T is used. 0 As a reference, the displacement of the same key points of the human body between two frames is used to determine the change of the image, and then to determine the next time interval. If the movement amplitude is larger, it means that the movement speed is faster. In order to capture more movement information, the formula is used Reduce the frame extraction time interval. Conversely, increase the frame extraction time interval to reduce the computing load.

[0104] (4) Feature extraction

[0105] The features in this application include posture features and motion features. Posture features are used to determine whether the posture of the current staff is normal, whether there are abnormal postures such as slipping, lying down, covering the head, covering the face, etc. Motion features are used to determine whether the current staff is making large movements in dangerous areas, such as large movements of the hands in switch areas, high-voltage areas, etc. Then, risk judgment is made, including:

[0106] Construct motion vectors based on the same human key points of any two adjacent images of people, and construct motion features based on all motion vectors; and connect the human key points of each frame of the image of the person to obtain posture features;

[0107] An action feature is constructed based on the motion feature and the posture feature.

[0108] S250, judging whether the current employee is at risk based on the action characteristics of the current employee, and sending an alarm message to the Internet of Things terminal of the current employee when there is a risk.

[0109] Risk assessment criteria include:

[0110] (1) When there is a dangerous area within the work activity range, determine whether there is a target motion vector located in the dangerous area and whose modulus is greater than a preset length threshold, and match the posture feature with a pre-constructed dangerous posture feature template; when there is a target motion vector, or there is a posture feature matching the dangerous posture feature template, determine that the current employee is at risk;

[0111] For example, if the hand moves significantly in the switch area or high-voltage area, the corresponding target motion vector will be large. At this time, an alarm is issued, and the alarm information is sent to the UWB terminal carried by the staff, prompting the staff to slow down their movements to avoid accidental touches caused by large movements. If the staff has an abnormal posture, that is, when it matches the dangerous posture feature template, it means that the staff has an abnormal posture, such as slipping, lying down, covering the head, covering the face, etc. An alarm is also issued at this time.

[0112] Specifically, for the matching of human body postures, this application adopts a deep learning method to determine the matching degree between the two by constructing a matching model.

[0113] (2) When there is no dangerous area in the work activity range, the posture feature is matched with a pre-constructed dangerous posture feature template; and when there is a posture feature that matches the dangerous posture feature template, it is determined that the current employee is at risk.

[0114] If there is no dangerous area in the worker's working range, then only the corresponding posture features need to be focused on.

[0115] The present invention provides an intelligent business management and control method based on the Internet of Things, which locates the current staff based on the wireless technology of the Internet of Things, and starts the safety management and control program when the current staff is in place in the corresponding area. During the safety management and control process, the current staff is filmed and the motion characteristics of the staff are extracted to monitor the safety of the staff in real time. If there is a safety risk, the alarm information is directly sent to the Internet of Things terminal on the staff to correct their behavior. The present application is suitable for use in related scenarios of operating dangerous equipment, and can further ensure that the staff's actions are compliant and avoid safety hazards caused by some non-compliant actions.

[0116] like Figure 3As shown, the present application also provides an intelligent business management and control system based on the Internet of Things, including:

[0117] An acquisition module, used to acquire the task content and indoor location of the current employee, wherein the indoor location is determined based on the distance measurement of multiple IoT base stations and the IoT terminal on the employee;

[0118] A scoping module for determining the scope of work activities of a current employee based on the task content of the current employee and a pre-built reference database;

[0119] A video acquisition module, configured to acquire regional video of the work activity range based on a preset camera when the indoor location of the current employee falls within the work activity range;

[0120] A feature extraction module, used to extract a regional image from the regional video, extract a person image from the regional image, and extract key points of a human body from the person image, extract frames of the regional video based on motion features of the key points of the human body to obtain multiple frames of person images, and determine the motion features of the current employee based on the key points of the human body in the multiple frames of person images;

[0121] The security management and control module is used to determine whether the current employee is at risk based on the action characteristics of the current employee, and send an alarm message to the Internet of Things terminal of the current employee when there is a risk.

[0122] The present invention provides an intelligent business management and control system based on the Internet of Things, which locates the current staff based on the wireless technology of the Internet of Things, and starts the safety management and control program when the current staff is in place in the corresponding area. During the safety management and control process, the current staff is filmed and the motion characteristics of the staff are extracted to monitor the safety of the staff in real time. If there is a safety risk, the alarm information is directly sent to the Internet of Things terminal on the staff to correct their behavior. The present application is suitable for use in related scenarios of operating dangerous equipment, and can further ensure that the staff's actions are in compliance and avoid safety hazards caused by some non-compliant actions.

[0123] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, any one of the methods in this embodiment is implemented, wherein the method is the execution logic of this system.

[0124] This embodiment also provides an electronic terminal, including: a processor and a memory;

[0125] The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes any one of the methods in this embodiment.

[0126] The computer-readable storage medium in this embodiment can be understood by ordinary technicians in this field: all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

[0127] The electronic terminal provided in this embodiment includes a processor, a memory, a transceiver and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store computer programs, the communication interface is used to communicate, and the processor and the transceiver are used to run computer programs so that the electronic terminal executes each step of the above method.

[0128] In this embodiment, the memory may include a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0129] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0130] In the above-mentioned embodiments, although the present invention has been described in conjunction with the specific embodiments of the present invention, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art according to the foregoing description. The embodiments of the present invention are intended to cover all such replacements, modifications and variations falling within the broad scope of the appended claims.

[0131] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. An intelligent business management and control method based on the Internet of Things, characterized in that: Includes steps: Obtaining the task content and indoor location of the current employee, wherein the indoor location is determined based on the distance measurement of multiple IoT base stations and the IoT terminal on the employee; Determining the scope of work activities of the current employee based on the task content of the current employee and a pre-built reference database; When the indoor location of the current employee falls within the work activity range, collecting a regional video of the work activity range based on a preset camera; Extracting a regional image from the regional video, extracting a person image from the regional image, and extracting key points of a human body from the person image, extracting frames from the regional video based on motion features of the key points of the human body to obtain multiple frames of person images, and determining motion features of the current employee based on the key points of the human body in the multiple frames of person images; It is determined whether the current employee is at risk based on the action characteristics of the current employee, and when there is a risk, an alarm message is sent to the Internet of Things terminal of the current employee.

2. According to claim 1, the intelligent operation and control method based on the Internet of Things is characterized in that: Get the current employee's indoor location, including: Regularly obtain the distance value S between multiple IoT base stations and the IoT terminal of the current employee i ; Based on the coordinates of multiple IoT base stations (x i ,y i ,z i ) and the coordinates of the current employee's Internet of Things terminal (x0, y0, z0) to construct multiple distance coordinate formulas, wherein the multiple distance coordinate formulas are: Based on the least squares method, multiple distance coordinate formulas are fitted to obtain the current employee's indoor positioning (x0, y0, z0).

3. According to the method of intelligent operation and control based on the Internet of Things in claim 1, it is characterized in that: The method for constructing the reference database comprises: S1, obtain historical positioning records corresponding to various tasks; S2, merge the positioning points in the historical positioning records of each job into the same coordinate system; S3, calculating the average value of all the positioning points in the coordinate system to obtain a reference positioning point; and using the reference positioning point as the current positioning point; S4, calculating the distances between all adjacent positioning points of the current positioning point and the current positioning point, and retaining target positioning points whose distances are less than a preset distance threshold; S5, taking the retained target positioning point as the current positioning point, and returning to step S4 until all target positioning points are obtained; S6, curve fitting is performed on the outermost target positioning points to obtain the work activity range of each job, and a reference database is constructed based on multiple jobs and the work activity ranges of multiple jobs.

4. The method for intelligent operation and control based on the Internet of Things according to claim 1, characterized in that: Extracting a person image from the region image, and extracting key points of a human body from the person image, comprising: A person image in the area image is extracted based on a pre-constructed human recognition model, and human key points in the person image are extracted based on a pre-constructed human feature point recognition model, wherein the human key points include a plurality of human bone joints.

5. According to claim 4, the intelligent operation and control method based on the Internet of Things is characterized in that: Extracting frames of the regional video based on the motion features of the human body key points includes: Get the current time extraction interval T0, extract two image frames based on the current time extraction interval T0, and calculate the distance S between the same human key points in the two image frames j , where j is the serial number of the key point of the human body; Calculate all distances S j The average And based on the average value S j Calculate the time interval T0′ for the next image extraction, where the mathematical expression of the time interval T0′ for the next image extraction is: Where S is the reference value of the moving distance; The next frame extraction is performed based on the time interval T0′ of the next image extraction.

6. The method for intelligent operation and control based on the Internet of Things according to claim 5, characterized in that: The action features of the current employee based on the key points of the human body of the multiple frames of personnel images include: Construct motion vectors based on the same human key points of any two adjacent images of people, and construct motion features based on all motion vectors; and connect the human key points of each frame of the image of the person to obtain posture features; An action feature is constructed based on the motion feature and the posture feature.

7. The method for intelligent operation and control based on the Internet of Things according to claim 6, characterized in that: Judging whether the current employee is at risk based on the action characteristics of the current employee includes: When there is a dangerous area in the work activity range, determine whether there is a target motion vector located in the dangerous area and whose modulus is greater than a preset length threshold, and match the posture feature with a pre-constructed dangerous posture feature template; when there is a target motion vector, or there is a posture feature that matches the dangerous posture feature template, determine whether the current employee is at risk; When there is no dangerous area in the working activity range, the posture feature is matched with a pre-constructed dangerous posture feature template; and when there is a posture feature matching the dangerous posture feature template, it is determined that the current employee is at risk.

8. An intelligent business management and control system based on the Internet of Things, characterized in that: include: An acquisition module, used to acquire the task content and indoor location of the current employee, wherein the indoor location is determined based on the distance measurement of multiple IoT base stations and the IoT terminal on the employee; A scoping module for determining the scope of work activities of a current employee based on the task content of the current employee and a pre-built reference database; A video acquisition module, configured to acquire regional video of the work activity range based on a preset camera when the indoor location of the current employee falls within the work activity range; A feature extraction module, used to extract a regional image from the regional video, extract a person image from the regional image, and extract key points of a human body from the person image, extract frames of the regional video based on motion features of the key points of the human body to obtain multiple frames of person images, and determine the motion features of the current employee based on the key points of the human body in the multiple frames of person images; The security management and control module is used to determine whether the current employee is at risk based on the action characteristics of the current employee, and send an alarm message to the Internet of Things terminal of the current employee when there is a risk.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the intelligent business management and control method based on the Internet of Things as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is enabled to execute the intelligent business management and control method based on the Internet of Things as described in any one of claims 1 to 7.

Images